{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T02:45:08Z","timestamp":1781837108455,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":26,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,6,23]],"date-time":"2024-06-23T00:00:00Z","timestamp":1719100800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,6,23]]},"DOI":"10.1145\/3649329.3656518","type":"proceedings-article","created":{"date-parts":[[2024,11,7]],"date-time":"2024-11-07T19:27:22Z","timestamp":1731007642000},"page":"1-6","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["VITA: ViT Acceleration for Efficient 3D Human Mesh Recovery via Hardware-Algorithm Co-Design"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-6310-2787","authenticated-orcid":false,"given":"Shilin","family":"Tian","sequence":"first","affiliation":[{"name":"University of Central Florida, Orlando, FL, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-2782-0932","authenticated-orcid":false,"given":"Chase","family":"Szafranski","sequence":"additional","affiliation":[{"name":"University of Central Florida, Olando, FL, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9033-0622","authenticated-orcid":false,"given":"Ce","family":"Zheng","sequence":"additional","affiliation":[{"name":"University of Central Florida, Orlando, FL, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0360-5641","authenticated-orcid":false,"given":"Fan","family":"Yao","sequence":"additional","affiliation":[{"name":"University of Central Florida, Orlando, FL, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4262-6688","authenticated-orcid":false,"given":"Ahmed","family":"Louri","sequence":"additional","affiliation":[{"name":"The George Washington University, Washinton, D.C., DC, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3957-7061","authenticated-orcid":false,"given":"Chen","family":"Chen","sequence":"additional","affiliation":[{"name":"University Of Central Florida, Orlando, FL, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4391-2774","authenticated-orcid":false,"given":"Hao","family":"Zheng","sequence":"additional","affiliation":[{"name":"University of Central Florida, Orlando, FL, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,11,7]]},"reference":[{"key":"e_1_3_2_1_1_1","first-page":"2269","volume-title":"Procc of AAAI","author":"Tianyu Luan","year":"2021","unstructured":"Tianyu Luan et al. Pc-hmr: Pose calibration for 3d human mesh recovery from 2d images\/videos. In Procc of AAAI, pages 2269--2276. AAAI Press, 2021."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3298850"},{"key":"e_1_3_2_1_3_1","volume-title":"Proc. of CVPR","author":"Ce","year":"2023","unstructured":"Ce Zheng et al. Potter: Pooling attention transformer for efficient human mesh recovery. In Proc. of CVPR, 2023."},{"key":"e_1_3_2_1_4_1","first-page":"15406","volume-title":"Recovering 3d human mesh from monocular images: A survey","author":"Yating Tian","year":"2022","unstructured":"Yating Tian et al. Recovering 3d human mesh from monocular images: A survey. pages 15406--15425. IEEE, 2022."},{"key":"e_1_3_2_1_5_1","volume-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale. In arXiv preprint arXiv:2010.11929","author":"Alexey Dosovitskiy","year":"2020","unstructured":"Alexey Dosovitskiy et al. An image is worth 16\u00d716 words: Transformers for image recognition at scale. In arXiv preprint arXiv:2010.11929, 2020."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00199"},{"key":"e_1_3_2_1_7_1","first-page":"901","volume-title":"TPAMI","author":"Xiaowei","year":"2018","unstructured":"Xiaowei Zhou et al. Monocap: Monocular human motion capture using a cnn coupled with a geometric prior. In TPAMI, pages 901--914. IEEE, 2018."},{"key":"e_1_3_2_1_8_1","first-page":"273","volume-title":"Proc. of HPCA","author":"Haoran","year":"2023","unstructured":"Haoran You et al. Vitcod: Vision transformer acceleration via dedicated algorithm and accelerator co-design. In Proc. of HPCA, pages 273--286. IEEE, 2023."},{"key":"e_1_3_2_1_9_1","first-page":"415","volume-title":"Proc. of HPCA","author":"Jyotikrishna","year":"2023","unstructured":"Jyotikrishna Dass et al. Vitality: Unifying low-rank and sparse approximation for vision transformer acceleration with a linear taylor attention. In Proc. of HPCA, pages 415--428. IEEE, 2023."},{"key":"e_1_3_2_1_10_1","first-page":"10012","volume-title":"Proc. of ICCV","author":"Ze","year":"2021","unstructured":"Ze Liu et al. Swin transformer: Hierarchical vision transformer using shifted windows. In Proc. of ICCV, pages 10012--10022, 2021."},{"key":"e_1_3_2_1_11_1","first-page":"166","volume-title":"Proc. of ICCD","author":"Lingxiang","year":"2023","unstructured":"Lingxiang Yin et al. Polyform: A versatile architecture for multi-dnn execution via spatial and temporal acceleration. In Proc. of ICCD, pages 166--169, 2023."},{"key":"e_1_3_2_1_12_1","volume-title":"Proc","author":"Junhyeong Cho","year":"2022","unstructured":"Junhyeong Cho et al. Cross-attention of disentangled modalities for 3d human mesh recovery with transformers. In Proc. of ECCV. Springer, 2022."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"key":"e_1_3_2_1_14_1","first-page":"577","volume-title":"Proc. of DAC","author":"Joonsang","year":"2022","unstructured":"Joonsang Yu et al. Nn-lut: neural approximation of non-linear operations for efficient transformer inference. In Proc. of DAC, pages 577--582, 2022."},{"key":"e_1_3_2_1_15_1","volume-title":"Gaussian error linear units (gelus). In arXiv preprint arXiv:1606.08415","author":"Hendrycks Dan","year":"2016","unstructured":"Dan Hendrycks and Kevin Gimpel. Gaussian error linear units (gelus). In arXiv preprint arXiv:1606.08415, 2016."},{"key":"e_1_3_2_1_16_1","first-page":"489","volume-title":"Proc. of GLSVLSI","author":"Lingxiang","year":"2023","unstructured":"Lingxiang Yin et al. Exploring architecture, dataflow, and sparsity for gcn accelerators: A holistic framework. In Proc. of GLSVLSI, page 489--495, 2023."},{"key":"e_1_3_2_1_17_1","first-page":"1","volume-title":"Proc. of ICCAD","author":"Lingxiang","year":"2023","unstructured":"Lingxiang Yin et al. Aries: Accelerating distributed training in chiplet-based systems via flexible interconnects. In Proc. of ICCAD, pages 1--9, 2023."},{"key":"e_1_3_2_1_18_1","volume-title":"Layer normalization. In arXiv preprint arXiv:1607.06450","author":"Ba Jimmy Lei","year":"2016","unstructured":"Jimmy Lei Ba et al. Layer normalization. In arXiv preprint arXiv:1607.06450, 2016."},{"key":"e_1_3_2_1_19_1","volume-title":"Resnet strikes back: An improved training procedure in timm. In arXiv preprint arXiv:2110.00476","author":"Ross Wightman","year":"2021","unstructured":"Ross Wightman et al. Resnet strikes back: An improved training procedure in timm. In arXiv preprint arXiv:2110.00476, 2021."},{"key":"e_1_3_2_1_20_1","first-page":"5314","volume-title":"Proc. of ICML","author":"Hugo","year":"2022","unstructured":"Hugo Touvron et al. Resmlp: Feedforward networks for image classification with data-efficient training. In Proc. of ICML, pages 5314--5321. IEEE, 2022."},{"key":"e_1_3_2_1_21_1","first-page":"248","volume-title":"Proc. of CVPR","author":"Jia","year":"2009","unstructured":"Jia Deng et al. Imagenet: A large-scale hierarchical image database. In Proc. of CVPR, pages 248--255. Ieee, 2009."},{"key":"e_1_3_2_1_22_1","volume-title":"Proc. in ECCV, sep","author":"Timo","year":"2018","unstructured":"Timo von Marcard et al. Recovering accurate 3d human pose in the wild using imus and a moving camera. In Proc. in ECCV, sep 2018."},{"key":"e_1_3_2_1_23_1","first-page":"10347","volume-title":"Proc. of ICML","author":"Hugo","year":"2021","unstructured":"Hugo Touvron et al. Training data-efficient image transformers & distillation through attention. In Proc. of ICML, pages 10347--10357. PMLR, 2021."},{"key":"e_1_3_2_1_24_1","volume-title":"Human3. 6m: Large scale datasets and predictive methods for 3d human sensing in natural environments","author":"Catalin Ionescu","year":"2013","unstructured":"Catalin Ionescu et al. Human3. 6m: Large scale datasets and predictive methods for 3d human sensing in natural environments. IEEE transactions on pattern analysis and machine intelligence, 36(7):1325--1339, 2013."},{"key":"e_1_3_2_1_25_1","first-page":"459","volume-title":"Proc. of the CVPR","author":"Georgios","year":"2018","unstructured":"Georgios Pavlakos et al. Learning to estimate 3d human pose and shape from a single color image. In Proc. of the CVPR, pages 459--468, 2018."},{"key":"e_1_3_2_1_26_1","first-page":"12939","volume-title":"Proc. of the ICCV","author":"Kevin","year":"2021","unstructured":"Kevin Lin et al. Mesh graphormer. In Proc. of the ICCV, pages 12939--12948, 2021."}],"event":{"name":"DAC '24: 61st ACM\/IEEE Design Automation Conference","location":"San Francisco CA USA","acronym":"DAC '24","sponsor":["SIGDA ACM Special Interest Group on Design Automation","IEEE-CEDA","SIGBED ACM Special Interest Group on Embedded Systems"]},"container-title":["Proceedings of the 61st ACM\/IEEE Design Automation Conference"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3649329.3656518","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3649329.3656518","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:55Z","timestamp":1750295875000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3649329.3656518"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,23]]},"references-count":26,"alternative-id":["10.1145\/3649329.3656518","10.1145\/3649329"],"URL":"https:\/\/doi.org\/10.1145\/3649329.3656518","relation":{},"subject":[],"published":{"date-parts":[[2024,6,23]]},"assertion":[{"value":"2024-11-07","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}